Vehicle Network Proxy Model for User Experience Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle-based communication systems face challenges in evaluating user experience due to low feedback rates from surveys and the inability to identify key factors affecting user satisfaction, particularly in the absence of direct feedback.
Innovation Solution
A proxy model is generated using machine learning techniques to analyze operational parameters, including hardware components, network states, user behavior, and service parameters, to quantify user experience without direct feedback, employing supervised and unsupervised learning methods to create a model that predicts user satisfaction scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If survey-based feedback methods are used to evaluate user experience, then direct user input is obtained, but response rates are low and key factors affecting satisfaction are not identified
Solution Approach 1:
The patent introduces a proxy model as an intermediary between operational parameters and user experience evaluation. Instead of directly surveying users, the system uses machine learning models trained on operational data to proxy for user experience assessment, thereby avoiding low survey response rates while maintaining measurement accuracy through indirect but reliable inference
Solution Approach 2:
The patent replaces the mechanical survey-based feedback collection system with an automated machine learning-based proxy evaluation system. This substitution eliminates the need for manual user participation while achieving more precise and continuous user experience measurement through algorithmic analysis of operational parameters
2Reliability
If system provider parameters are used to evaluate network performance, then network operation metrics are available, but these parameters do not match user assessment criteria
Solution Approach 1:
The patent transforms system provider operational parameters into user experience-relevant parameters through machine learning model training. The proxy models learn the mapping between provider-side metrics (e.g., network throughput, latency) and user-perceived quality, adjusting and reweighting parameters to reflect actual user assessment criteria rather than purely technical specifications
Solution Approach 2:
The patent analyzes a comprehensive set of operational parameters beyond what traditional monitoring includes, using machine learning to identify which parameters most strongly correlate with user experience. This excessive analysis of available data ensures that no potentially relevant factor is missed, allowing the model to capture nuanced relationships between system operation and user satisfaction
Data Source
AI summary
A machine learning-based proxy model may be generated to determine quality of user experience in a vehicle-based communication network in the absence of direct feedback from the users regarding the user experience. The machine learning-based proxy model may include supervised and/or unsupervised machine learning models, including for example a k-means clustering algorithm and/or an artificial neural network. Once generated, the proxy model may be applied to observed operational parameters of the vehicle-based communication network to quantify the user experience for any user for any duration of the vehicle-based communication network.